diff --git a/examples/text_to_image/train_text_to_image.py b/examples/text_to_image/train_text_to_image.py
index 6c45ee0b1b..8aac7b6b5b 100644
--- a/examples/text_to_image/train_text_to_image.py
+++ b/examples/text_to_image/train_text_to_image.py
@@ -493,7 +493,7 @@ def main():
 
     train_transforms = transforms.Compose(
         [
-            transforms.Resize((args.resolution, args.resolution), interpolation=transforms.InterpolationMode.BILINEAR),
+            transforms.Resize(args.resolution, interpolation=transforms.InterpolationMode.BILINEAR),
             transforms.CenterCrop(args.resolution) if args.center_crop else transforms.RandomCrop(args.resolution),
             transforms.RandomHorizontalFlip() if args.random_flip else transforms.Lambda(lambda x: x),
             transforms.ToTensor(),
diff --git a/examples/text_to_image/train_text_to_image_flax.py b/examples/text_to_image/train_text_to_image_flax.py
index b3379226f2..4554cdd082 100644
--- a/examples/text_to_image/train_text_to_image_flax.py
+++ b/examples/text_to_image/train_text_to_image_flax.py
@@ -333,7 +333,7 @@ def main():
 
     train_transforms = transforms.Compose(
         [
-            transforms.Resize((args.resolution, args.resolution), interpolation=transforms.InterpolationMode.BILINEAR),
+            transforms.Resize(args.resolution, interpolation=transforms.InterpolationMode.BILINEAR),
             transforms.CenterCrop(args.resolution) if args.center_crop else transforms.RandomCrop(args.resolution),
             transforms.RandomHorizontalFlip() if args.random_flip else transforms.Lambda(lambda x: x),
             transforms.ToTensor(),